Elastic, the Search AI Company, announced a new integration with Azure AI Foundry, delivering observability for agentic AI applications and large language models. The integration provides site reliability engineers and developers with real-time insights into LLMs, generative AI and agentic AI workloads, enabling them to build, monitor, and optimize intelligent agents on Azure AI Foundry with greater reliability and efficiency while also including guardrails.
As organizations adopt agentic AI for mission-critical applications, they face challenges such as uncontrolled token usage, latency bottlenecks, and compliance blind spots. Elastic’s integration with Azure AI Foundry addresses these issues with pre-built dashboards that deliver real-time insights into model usage, performance, costs and content filtering—all in a unified view.
“Agentic AI is only as strong as the models and infrastructure that power it,” said Santosh Krishnan, general manager, Observability & Security at Elastic. “With Elastic and Azure AI Foundry, developers and SREs gain clear visibility into how their agents are performing, understand the drivers of cost, and fix performance bottlenecks in real time. That means they can scale AI applications faster without compromising reliability, compliance, or budget.”
“This integration with Elastic delivers real-time visibility into token usage, latency, and costs, with built-in safeguards for any model hosted in Azure AI Foundry,” said Amanda Silver, corporate vice president at Microsoft Azure CoreAI. “Developers can now build and scale agents on Azure AI Foundry with the operational clarity and control they need to succeed in production.”
